Peacemaker at ATE-IT: Automatic term extraction from Italian text for waste management data using encoder model
Researchers have developed a novel method for automatic term extraction from Italian text, specifically for waste management data. This approach utilizes an encoder model and fine-tuning strategies that require minimal computational resources. The system demonstrated consistent and balanced performance in the ATE Shared Task, serving as a strong baseline for low-resource models while maintaining interpretability. AI
IMPACT This research offers a low-resource, interpretable solution for domain-specific term extraction, potentially improving data analysis in specialized fields.